persona-skeptic
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown content defining a 'Skeptic' persona. It provides guidelines for auditing work, such as re-running commands, verifying requirements by ID, and performing adversarial self-reviews.
- [NO_CODE]: There are no executable scripts, shell commands, or external dependencies defined within this skill file.
- [SAFE]: No sensitive data access, exfiltration patterns, obfuscation, or prompt injection attempts were detected. The use of authoritative language (e.g., 'ALWAYS apply', 'Refuse') is scoped to the logic of performing a rigorous technical review rather than overriding agent safety protocols.
Audit Metadata